Agent Rigor – Stop your AI coding assistant from doom-looping

Notifications You must be signed in to change notification settings

Fork 0

Star 2

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

8 Commits

8 Commits

assets

assets

examples

examples

skills

skills

templates

templates

.gitignore

.gitignore

CHEATSHEET.md

CHEATSHEET.md

CONTEXT_MANAGEMENT.md

CONTEXT_MANAGEMENT.md

CONTRIBUTING.md

CONTRIBUTING.md

QUICKSTART.md

QUICKSTART.md

README.md

README.md

SYSTEM_CORE.md

SYSTEM_CORE.md

install.sh

install.sh

Repository files navigation

Strict empirical discipline for your AI coding assistant.

Stop watching your AI agent code itself into a corner. Give it discipline.

Quickstart • Philosophy • Architecture • Supported Agents

🚀 Why Agent Rigor?

Most AI coding agents fail not because they lack intelligence, but because they lack discipline. When left to their own devices, they:

❌ Skip planning and jump straight to implementation.

❌ Write plausible-looking code that doesn't actually work.

❌ Get trapped in "doom loops" (fix-forward spirals).

❌ Forget what they learned between sessions (context amnesia).

❌ Suffer from "context rot" by loading too many instructions at once.

Agent Rigor solves this. It provides a structured, multi-layer progressive disclosure framework: a set of mandatory protocols, verification gates, and anti-rationalization safeguards that force empirical discipline at every step.

🛡️ Core Philosophy

Actionable Protocols: Every instruction is a verifiable step with exit criteria, not an essay.

Empirical Sovereignty: Claims require evidence. "Seems right" is never sufficient.

Atomic State Transitions: The codebase moves between known-good states. Broken states are never committed.

Anti-Rationalization: Every skill actively anticipates and rebuts the excuses agents use to skip discipline.

Progressive Disclosure: The agent reads only the files it needs for the current phase, saving tokens and preventing instruction neglect.

🏗️ Architecture

The system is organized into a robust 3-tier hierarchy using Progressive Disclosure to prevent context window collapse.

The 3-Tier Context Hierarchy

L1: Apex Kernel (SYSTEM_CORE.md): Always-on routing and non-negotiable laws.

L2: Phase Directors (00_PHASE_DIRECTOR.md): Just-in-time orchestration loaded only when entering a phase.

L3: Skill Protocols (skills/*.md): Deep execution guidelines loaded only when requested by the Director.

The Operational Loop

graph TD A[Phase 1: Mission Synthesis] -->|PLAN.md| B(Phase 2: Execution Engine) B -->|Committed Code| C{Phase 3: Verification Matrix} C -->|CRITICAL Findings| B C -->|Zero Findings| D[Phase 4: Cognitive Persistence] D -->|Context Snapshot| A

subgraph Phase 6: Adaptive Protocols Z[Self-Correction / Scope Defense / Consolidation] end

B -.->|3-Strike Failure| Z Z -.->|Recovery| B

Loading

🛠️ The 6 Operational Phases

Phase Purpose Key Skills

1. Mission Synthesis

Requirements & Planning Requirement Distillation, Strategic Decomposition

1. Execution Engine

Implementation & Testing Convergent Iteration, State Checkpointing

1. Verification Matrix

Quality & Review Gates Pentagonal Audit, Entropy Reduction

1. Cognitive Persistence

Memory & Knowledge Context Lifecycle, Structural Cartography

1. Interface Protocols

Safe Environment Interaction Bounded Observation, Semantic Navigation

1. Adaptive Protocols

The Immune System Recursive Self-Correction, Scope Containment

⚡ Quickstart

Get Agent Rigor working in your project in under 2 minutes.

1. Bootstrap Your Project

Run the installation script in your project root:

curl -sSL https://raw.githubusercontent.com/MeherBhaskar/agent-rigor/main/install.sh | bash

(Alternatively, clone this repo into an .agents/ directory).

1. Tell Your Agent to Start

Simply prompt your agent with:

"I need to build [feature]. Read .agents/SYSTEM_CORE.md and begin Phase 1 (Mission Synthesis)."

The agent will automatically read the Phase 1 Director, create a PLAN.md, and orchestrate its own work through implementation, review, and context saving.

🤖 Supported Agents

Agent Rigor is pure markdown and platform-agnostic. It works natively with:

Agent / IDE Integration Method

Cursor Point to .agents/SYSTEM_CORE.md in your .cursorrules or .mdc files.

Claude Code Include a reference in your CLAUDE.md.

GitHub Copilot Reference in .github/copilot-instructions.md.

Gemini CLI / Antigravity Include in .agents/AGENTS.md.

Aider Pass via --read .agents/SYSTEM_CORE.md.

See the examples/ folder for ready-to-use configuration templates.

🤝 Contributing

We welcome contributions to make agents smarter and more disciplined! Please see our Contributing Guidelines to understand how to design skills that agents actually follow.

If this framework saves your agent from a doom loop, consider leaving a ⭐!

About

A self-sufficient operating system for autonomous coding agents.

Resources

Readme

Contributing

Contributing

Uh oh!

There was an error while loading. Please reload this page.

Activity

Stars

2 stars

Watchers

0 watching

Forks

0 forks

Report repository

Releases

No releases published

Packages 0

Uh oh!

There was an error while loading. Please reload this page.

Contributors

Uh oh!

There was an error while loading. Please reload this page.

Languages

Shell 100.0%